SILMA TTS v2.0 Model & API
SILMA TTS Models are state-of-the-art Multilingual Text-to-Speech models and APIs offering natural-sounding synthesis for English, Modern Standard Arabic (Fus'ha) and Saudi Najdi dialect, purposely designed for your voice agent platform.
Create a Free Account
Create a Free Account
SILMA TTS v2.0
Low streaming latency with ~170ms TTFT - excluding network
Latency Performance
Below is a comparison of SILMA TTS v2 against leading competitors in terms of latency and pricing, based on recent 2026 benchmark data (with calls placed from the EU after warm-up)
Integrate our Text to Speech API
Integrating our API is simple: log in to our application, generate your API key, and then follow our API tutorial and specifications.
In addition, we provide plugins for the following frameworks
Pipecat
pip install pipecat-silma
Use cases for every voice experience
Voice Agents
Natural, responsive conversations that help customers get answers, take action, and stay engaged.
Applications
Bring expressive, multilingual speech to products people use every day — from learning to accessibility.
Robots
Give physical AI a clear, trusted voice for guidance, interaction, and real-world assistance.
FAQ
What is the end-to-end TTFT latency, including network time?
Which languages are supported?
Do you support pronouncing phone numbers and email addresses?
What is the maximum input length (number of characters allowed)?